Surface modification processes by electrons, photons, ions and plasmas typically feature a high-dimensional and extensive process parameter space. Exploring this space purely through experiments can be highly resource-intensive, making the search for optimum process conditions costly. We employ modern machine learning techniques to shorten this effort. Gaussian processes for example offer a flexible, non-parametric approach to modeling a response surface from input data with the goal of predicting the response for unseen inputs. In addition, they inherently provide a quantification of uncertainty in the response, which is variable across the input space and naturally increases in regions with no data. A second key characteristics is its ability to iteratively update the GP model as new data is collected. Based on the currently modeled response and its local uncertainty, data can be strategically collected at locations with high uncertainty in order to maximize model refinement while minimizing effort. The refined model can then be exploited to predict the process parameters that yield the optimum process outcome.